---
id: "fish-audio/transcribe-1"
also: ["fish-audio/transcribe-1-20260729", "vercel/fish-audio/transcribe-1"]
card_usd_per_m: "100.0 in, 0.0 out, at fish-audio"
cheapest_list_usd_per_m: "0.0001 in, 0.0 out, at fish-audio on vercel"
cheapest_effective_usd_per_m: "0.0001 in, 0.0 out, at fish-audio on vercel"
context: 0
max_output: 0
input: ["audio"]
output: ["transcription"]
released: "2026-07-29"
api: ["/api/v1/audio/transcriptions"]
params: ["max_tokens", "stop", "temperature"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 1
trains: 1
retains_prompts: 1
---
# Fish Audio: Transcribe 1

Transcribe 1 is a speech-to-text model from Fish Audio. It is suited for audio transcription with automatic language detection and can return timestamped word-level segments when alignment details are requested.